AI Compute Radar MCP Server

by aicomputeradar Your server? Claim it

answering

AI Compute Radar is answering right now. Last checked 9 min ago. It exposes 5 tools.

Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.

Uptime history 5 days of history

5 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

258 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 21 September 2026. No other catalogue keeps this.

21 Sep a tool description was rewritten gpu_prices

Nothing serious here today

Today is the operative word: we check AI Compute Radar every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add ai-compute-radar --transport http https://aicomputeradar.dev/api/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ai-compute-radar": {
      "url": "https://aicomputeradar.dev/api/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.ai-compute-radar]
url = "https://aicomputeradar.dev/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "ai-compute-radar": {
      "url": "https://aicomputeradar.dev/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "ai-compute-radar": {
      "url": "https://aicomputeradar.dev/api/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

fit

find_fit

Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.

gpu

gpu_prices

Median verified on-demand rental price per GPU class on Vast.ai (USD per hour), with min/p75 and offer counts, the collection timestamp, and per class the Rent Index: this week's median against last week and against the first week collected, a trend word, and the days excluded as marketplace glitches, plus RunPod's lowest posted on-demand price per class (a list price, not a median). The index describes what prices did; it never forecasts.

hardware

list_hardware

Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.

trending

trending_models

Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have heat=null and rank after scored ones.

weekly

weekly_pick

The current pick of the week: one tracked model chosen by a published rule (largest counted Heat Score rise among models that run comfortably on a consumer card of up to 24 GB), with the numbers frozen at selection time, a device-by-device fit ladder and the written report including its caveats. Pass week (e.g. 2026-w37) for a past issue. issue is null until the first issue is published.

Endpoints

URL	Transport	State	Latency	Checked
https://aicomputeradar.dev/api/mcp	streamable-http	answering	105 ms	9 min ago

Alternatives to AI Compute Radar

same job, measured the same way

Compute Finance Oracle

by compute-finance

Live AI compute pricing oracle — real-time LLM model prices across providers

226 installs/wk local only

Glint Meet — every global model for your agent

by zzzjy765

Call every global AI model through one OpenAI-compatible API. One key, all models.

local only

Sighttrue

by kaitzyy-dev

Measured readings on open-source dependencies: health, end-of-life, model prices, incidents.

31 tools answering

Pickrate

by pickrate

Agent analytics: which AI agents read your site, drove signups, and pick you over competitors.

4 tools answering

Oriora Router

by orioralabs

AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.

answering

FastGPU

by fastgpu

Compare live GPU cloud rental prices and match workloads to the cheapest provider.

2 tools answering

GitWarren

by klarluft

Code review on your own machine, for you and your coding agent. Nothing leaves your computer.

582 installs/wk local only

Overllm

by theadamdanielsson

Find the LLM/AI calls you didn't need — where plain code or a regex does the job. No model.

148 installs/wk local only

AI Compute Radar — questions

Answers built from our own checks of this server.

What can AI Compute Radar do?

It exposes 5 tools, read directly from the server on our last check. Among them: find_fit, gpu_prices, list_hardware, trending_models, weekly_pick. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is AI Compute Radar working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 258 ms. The bar chart above shows every period we have measured.

How do I connect AI Compute Radar?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does AI Compute Radar need an API key?

No. AI Compute Radar completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is AI Compute Radar?

It answers our handshake in 258 ms on average, which is faster than 61% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.